System and method for identifying unmoved items on a platform during item identification

Abstract

In response to detecting a first triggering event corresponding to placement of a first item on a platform, a first image of the platform is captured. A first item identifier of the first item is identified and stored in a memory. In response to detecting a second triggering event corresponding to placement of a second item on the platform, a second image of the platform is captured. The second image is compared with the first image. Upon determining that the first item depicted in the second image overlaps with the first item depicted in the first image and the overlap equals or exceeds a threshold, the first item identifier is assigned to the first item depicted in the second image. A second item identifier of the second item is identified, and information associated with the first item identifier and the second item identifier is displayed on a user interface device.

The invention claimed is: 
     
         1 . An item tracking system, comprising:
 a plurality of cameras, wherein each camera is configured to capture images of at least a portion of a platform;   a user interface device; and   one or more processors communicatively coupled to the user interface device, and configured to:
 detect a first triggering event at the platform, wherein the first triggering event corresponds to a placement of a first item on the platform; 
 in response to detecting the first triggering event, capture a first image of the platform using a first camera of the plurality of cameras; 
 determine a first region within the first image that depicts the first item, wherein the first region includes a first group of pixels of the first image corresponding to the first item; 
 identify a first item identifier associated with the first item; 
 store, in a memory, the first item identifier of the first item associated with the first region; 
 display, on the user interface device, information associated with the first item identifier; 
 after detecting the first triggering event, detect a second triggering event at the platform, wherein the second triggering event corresponds to a placement of a second item on the platform; 
 in response to detecting the second triggering event, capture a second image of the platform using the first camera; 
 determine a second region within the second image that depicts the first item, wherein the second region includes a second group of pixels of the second image corresponding to the first item; 
 compare the second image to the first image; 
 determine that the second region of the second image overlaps with the first region of the first image and that the overlap equals or exceeds a pre-configured threshold overlap indicating that the first item has not moved on the platform since the detecting the first triggering event; 
 in response to determining that the overlap equals or exceeds the pre-configured threshold overlap, access from the memory the first item identifier of the first item associated with the first region; 
 assign the first item identifier to the first item depicted in the second region of the second image; 
 identify a second item identifier associated with the second item depicted in the second image; and 
 display, on the user interface device, information associated with the second item identifier along with the first item identifier. 
   
     
     
         2 . The item tracking system of  claim 1 , wherein the first camera is an overhead camera that is configured to capture overhead images of the platform. 
     
     
         3 . The item tracking system of  claim 1 , wherein the one or more processors are further configured to:
 in response to detecting the first triggering event, capture a plurality of third images of the first item on the platform using two or more cameras of the plurality of cameras;   generate a cropped third image for each of the third images by editing the third image to isolate at least a portion of the first item, wherein the cropped third images correspond to the first item in the respective third images;   assign a first group identifier to the cropped third images;   identify a plurality of different item identifiers based on the cropped third images;   present the plurality of different item identifiers on the user interface device;   receive a user selection of the first item identifier from the user interface device, wherein the first item identifier is selected from the plurality of different item identifiers;   map the first item identifier to the first group identifier; and   store in the memory the first item identifier mapped to the first group identifier of the cropped third images associated with the first item in the first region of the first image.   
     
     
         4 . The item tracking system of  claim 3 , wherein the one or more processors are further configured to:
 in response to determining that the overlap between the second region of the second image and the first region of the first image equals or exceeds the pre-configured threshold overlap, assign the first group identifier to the first item depicted in the second image of the platform;   access from the memory the first item identifier of the first item mapped to the first group identifier; and   display, on the user interface device, the first group identifier next to an indication of the first item identifier.   
     
     
         5 . The item tracking system of  claim 4 , wherein the one or more processors are further configured to:
 in response to detecting the second triggering event, capture a plurality of fourth images of the second item on the platform using two or more cameras of the plurality of cameras;   generate a cropped fourth image for each of the fourth images by editing the fourth image to isolate at least a portion of the second item, wherein the cropped fourth images correspond to the second item in the respective fourth images;   assign a second group identifier to the cropped fourth images;   identify the second item identifier associated with the second item based on the cropped fourth images; and   display, on the user interface device, the second group identifier next to an indication of the second item identifier.   
     
     
         6 . The item tracking system of  claim 5 , wherein the memory is configured to store:
 an encoded vector library, wherein the encoded vector library comprises a plurality of encoded vectors, wherein:
 each encoded vector comprises an array of numerical values; 
 each numerical value describes an attribute of a particular item based on an image of the particular item; 
 each encoded vector is associated with an item identifier for a particular item; and 
 each encoded vector is associated with a plurality of feature descriptors for a particular item, wherein the plurality of feature descriptors for the particular item describe physical characteristics of the particular item. 
   
     
     
         7 . The item tracking system of  claim 6 , wherein the one or more processors are configured to identify the second item identifier associated with the second item by:
 for each cropped fourth image:
 generating a first encoded vector for the cropped fourth image, wherein the first encoded vector describes an attribute of the second item based on the cropped fourth image; 
 compare the first encoded vector to the encoded vectors in the encoded vector library; 
 identify a second encoded vector in the encoded vector library that most closely matches the first encoded vector; and 
 identify the second item identifier in the encoded vector library that is associated with the second encoded vector. 
   
     
     
         8 . A method for identifying an item, comprising:
 detect a first triggering event at a platform, wherein the first triggering event corresponds to a placement of a first item on the platform;   in response to detecting the first triggering event, capture a first image of the platform using a first camera of a plurality of cameras, wherein each camera is configured to capture images of at least a portion of the platform;   determine a first region within the first image that depicts the first item, wherein the first region includes a first group of pixels of the first image corresponding to the first item;   identify a first item identifier associated with the first item;   store, in a memory, the first item identifier of the first item associated with the first region;   display, on a user interface device, information associated with the first item identifier;   after detecting the first triggering event, detect a second triggering event at the platform, wherein the second triggering event corresponds to a placement of a second item on the platform;   in response to detecting the second triggering event, capture a second image of the platform using the first camera;   determine a second region within the second image that depicts the first item, wherein the second region includes a second group of pixels of the second image corresponding to the first item;   compare the second image to the first image;   determine that the second region of the second image overlaps with the first region of the first image and that the overlap equals or exceeds a pre-configured threshold overlap indicating that the first item has not moved on the platform since the detecting the first triggering event;   in response to determining that the overlap equals or exceeds the pre-configured threshold overlap, access from the memory the first item identifier of the first item associated with the first region;   assign the first item identifier to the first item depicted in the second region of the second image;   identify a second item identifier associated with the second item depicted in the second image; and   display, on the user interface device, information associated with the second item identifier along with the first item identifier.   
     
     
         9 . The method of  claim 8 , wherein the first camera is an overhead camera that is configured to capture overhead images of the platform. 
     
     
         10 . The method of  claim 8 , further comprising:
 in response to detecting the first triggering event, capturing a plurality of third images of the first item on the platform using two or more cameras of the plurality of cameras;   generating a cropped third image for each of the third images by editing the third image to isolate at least a portion of the first item, wherein the cropped third images correspond to the first item in the respective third images;   assigning a first group identifier to the cropped third images;   identifying a plurality of different item identifiers based on the cropped third images;   presenting the plurality of different item identifiers on the user interface device;   receiving a user selection of the first item identifier from the user interface device, wherein the first item identifier is selected from the plurality of different item identifiers;   mapping the first item identifier to the first group identifier; and   storing in the memory the first item identifier mapped to the first group identifier of the cropped third images associated with the first item in the first region of the first image.   
     
     
         11 . The method of  claim 10 , further comprising:
 in response to determining that the overlap between the second region of the second image and the first region of the first image equals or exceeds the pre-configured threshold overlap, assigning the first group identifier to the first item depicted in the second image of the platform;   accessing from the memory the first item identifier of the first item mapped to the first group identifier; and   displaying, on the user interface device, the first group identifier next to an indication of the first item identifier.   
     
     
         12 . The method of  claim 11 , further comprising:
 in response to detecting the second triggering event, capturing a plurality of fourth images of the second item on the platform using two or more cameras of the plurality of cameras;   generating a cropped fourth image for each of the fourth images by editing the fourth image to isolate at least a portion of the second item, wherein the cropped fourth images correspond to the second item in the respective fourth images;   assigning a second group identifier to the cropped fourth images;   identifying the second item identifier associated with the second item based on the cropped fourth images; and   displaying, on the user interface device, the second group identifier next to an indication of the second item identifier.   
     
     
         13 . The method of  claim 12 , wherein the memory is configured to store:
 an encoded vector library, wherein the encoded vector library comprises a plurality of encoded vectors, wherein:
 each encoded vector comprises an array of numerical values; 
 each numerical value describes an attribute of a particular item based on an image of the particular item; 
 each encoded vector is associated with an item identifier for a particular item; and 
 each encoded vector is associated with a plurality of feature descriptors for a particular item, wherein the plurality of feature descriptors for the particular item describe physical characteristics of the particular item. 
   
     
     
         14 . The method of  claim 13 , wherein identifying the second item identifier associated with the second item comprises:
 for each cropped fourth image:
 generating a first encoded vector for the cropped fourth image, wherein the first encoded vector describes an attribute of the second item based on the cropped fourth image; 
 compare the first encoded vector to the encoded vectors in the encoded vector library; 
 identify a second encoded vector in the encoded vector library that most closely matches the first encoded vector; and 
 identify the second item identifier in the encoded vector library that is associated with the second encoded vector. 
   
     
     
         15 . A non-transitory computer-readable medium storing instructions that when executed by one or more processors cause the one or more processors to:
 detect a first triggering event at a platform, wherein the first triggering event corresponds to a placement of a first item on the platform;   in response to detecting the first triggering event, capture a first image of the platform using a first camera of a plurality of cameras, wherein each camera is configured to capture images of at least a portion of the platform;   determine a first region within the first image that depicts the first item, wherein the first region includes a first group of pixels of the first image corresponding to the first item;   identify a first item identifier associated with the first item;   store, in a memory, the first item identifier of the first item associated with the first region;   display, on a user interface device, information associated with the first item identifier;   after detecting the first triggering event, detect a second triggering event at the platform, wherein the second triggering event corresponds to a placement of a second item on the platform;   in response to detecting the second triggering event, capture a second image of the platform using the first camera;   determine a second region within the second image that depicts the first item, wherein the second region includes a second group of pixels of the second image corresponding to the first item;   compare the second image to the first image;   determine that the second region of the second image overlaps with the first region of the first image and that the overlap equals or exceeds a pre-configured threshold overlap indicating that the first item has not moved on the platform since the detecting the first triggering event;   in response to determining that the overlap equals or exceeds the pre-configured threshold overlap, access from the memory the first item identifier of the first item associated with the first region;   assign the first item identifier to the first item depicted in the second region of the second image;   identify a second item identifier associated with the second item depicted in the second image; and   
       display, on the user interface device, information associated with the second item identifier along with the first item identifier. 
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein the first camera is an overhead camera that is configured to capture overhead images of the platform. 
     
     
         17 . The non-transitory computer-readable medium of  claim 15 , wherein the instructions further cause the one or more processors to:
 in response to detecting the first triggering event, capture a plurality of third images of the first item on the platform using two or more cameras of the plurality of cameras;   generate a cropped third image for each of the third images by editing the third image to isolate at least a portion of the first item, wherein the cropped third images correspond to the first item in the respective third images;   assign a first group identifier to the cropped third images;   identify a plurality of different item identifiers based on the cropped third images;   present the plurality of different item identifiers on the user interface device;   receive a user selection of the first item identifier from the user interface device, wherein the first item identifier is selected from the plurality of different item identifiers;   map the first item identifier to the first group identifier; and   store in the memory the first item identifier mapped to the first group identifier of the cropped third images associated with the first item in the first region of the first image.   
     
     
         18 . The non-transitory computer-readable medium of  claim 17 , wherein the instructions further cause the one or more processors to:
 in response to determining that the overlap between the second region of the second image and the first region of the first image equals or exceeds the pre-configured threshold overlap, assign the first group identifier to the first item depicted in the second image of the platform;   access from the memory the first item identifier of the first item mapped to the first group identifier; and   display, on the user interface device, the first group identifier next to an indication of the first item identifier.   
     
     
         19 . The non-transitory computer-readable medium of  claim 18 , wherein the instructions further cause the one or more processors to:
 in response to detecting the second triggering event, capture a plurality of fourth images of the second item on the platform using two or more cameras of the plurality of cameras;   generate a cropped fourth image for each of the fourth images by editing the fourth image to isolate at least a portion of the second item, wherein the cropped fourth images correspond to the second item in the respective fourth images;   assign a second group identifier to the cropped fourth images;   identify the second item identifier associated with the second item based on the cropped fourth images; and   display, on the user interface device, the second group identifier next to an indication of the second item identifier.   
     
     
         20 . The non-transitory computer-readable medium of  claim 19 , wherein the memory is configured to store:
 an encoded vector library, wherein the encoded vector library comprises a plurality of encoded vectors, wherein:
 each encoded vector comprises an array of numerical values; 
 each numerical value describes an attribute of a particular item based on an image of the particular item; 
 each encoded vector is associated with an item identifier for a particular item; and 
 each encoded vector is associated with a plurality of feature descriptors for a particular item, wherein the plurality of feature descriptors for the particular item describe physical characteristics of the particular item; and 
   wherein identifying the second item identifier associated with the second item comprises:
 for each cropped fourth image:
 generating a first encoded vector for the cropped fourth image, wherein the first encoded vector describes an attribute of the second item based on the cropped fourth image; 
 compare the first encoded vector to the encoded vectors in the encoded vector library; 
 identify a second encoded vector in the encoded vector library that most closely matches the first encoded vector; and 
 
 identify the second item identifier in the encoded vector library that is associated with the second encoded vector.